diff mbox series

z3fold: fix retry mechanism in page reclaim

Message ID 20190908162919.830388dc7404d1e2c80f4095@gmail.com (mailing list archive)
State New, archived
Headers show
Series z3fold: fix retry mechanism in page reclaim | expand

Commit Message

Vitaly Wool Sept. 8, 2019, 1:29 p.m. UTC
z3fold_page_reclaim()'s retry mechanism is broken: on a second
iteration it will have zhdr from the first one so that zhdr
is no longer in line with struct page. That leads to crashes when
the system is stressed.

Fix that by moving zhdr assignment up.

While at it, protect against using already freed handles by using
own local slots structure in z3fold_page_reclaim().

Reported-by: Markus Linnala <markus.linnala@gmail.com>
Reported-by: Chris Murphy <bugzilla@colorremedies.com>
Reported-by: Agustin Dall'Alba <agustin@dallalba.com.ar>
Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
---
 mm/z3fold.c | 49 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 15 deletions(-)

Comments

Maciej S. Szmigiero Sept. 8, 2019, 1:56 p.m. UTC | #1
On 08.09.2019 15:29, Vitaly Wool wrote:
> z3fold_page_reclaim()'s retry mechanism is broken: on a second
> iteration it will have zhdr from the first one so that zhdr
> is no longer in line with struct page. That leads to crashes when
> the system is stressed.
> 
> Fix that by moving zhdr assignment up.
> 
> While at it, protect against using already freed handles by using
> own local slots structure in z3fold_page_reclaim().
> 
> Reported-by: Markus Linnala <markus.linnala@gmail.com>
> Reported-by: Chris Murphy <bugzilla@colorremedies.com>
> Reported-by: Agustin Dall'Alba <agustin@dallalba.com.ar>
> Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
> ---

Shouldn't this be CC'ed to stable@ ?

Maciej
Vitaly Wool Sept. 8, 2019, 8:44 p.m. UTC | #2
On Sun, Sep 8, 2019 at 4:56 PM Maciej S. Szmigiero
<mail@maciej.szmigiero.name> wrote:
>
> On 08.09.2019 15:29, Vitaly Wool wrote:
> > z3fold_page_reclaim()'s retry mechanism is broken: on a second
> > iteration it will have zhdr from the first one so that zhdr
> > is no longer in line with struct page. That leads to crashes when
> > the system is stressed.
> >
> > Fix that by moving zhdr assignment up.
> >
> > While at it, protect against using already freed handles by using
> > own local slots structure in z3fold_page_reclaim().
> >
> > Reported-by: Markus Linnala <markus.linnala@gmail.com>
> > Reported-by: Chris Murphy <bugzilla@colorremedies.com>
> > Reported-by: Agustin Dall'Alba <agustin@dallalba.com.ar>
> > Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
> > ---
>
> Shouldn't this be CC'ed to stable@ ?

I guess :)

Thanks,
   Vitaly
diff mbox series

Patch

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 75b7962439ff..6397725b5ec6 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -372,9 +372,10 @@  static inline int __idx(struct z3fold_header *zhdr, enum buddy bud)
  * Encodes the handle of a particular buddy within a z3fold page
  * Pool lock should be held as this function accesses first_num
  */
-static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
+static unsigned long __encode_handle(struct z3fold_header *zhdr,
+				struct z3fold_buddy_slots *slots,
+				enum buddy bud)
 {
-	struct z3fold_buddy_slots *slots;
 	unsigned long h = (unsigned long)zhdr;
 	int idx = 0;
 
@@ -391,11 +392,15 @@  static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
 	if (bud == LAST)
 		h |= (zhdr->last_chunks << BUDDY_SHIFT);
 
-	slots = zhdr->slots;
 	slots->slot[idx] = h;
 	return (unsigned long)&slots->slot[idx];
 }
 
+static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
+{
+	return __encode_handle(zhdr, zhdr->slots, bud);
+}
+
 /* Returns the z3fold page where a given handle is stored */
 static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h)
 {
@@ -630,6 +635,7 @@  static void do_compact_page(struct z3fold_header *zhdr, bool locked)
 	}
 
 	if (unlikely(PageIsolated(page) ||
+		     test_bit(PAGE_CLAIMED, &page->private) ||
 		     test_bit(PAGE_STALE, &page->private))) {
 		z3fold_page_unlock(zhdr);
 		return;
@@ -1132,6 +1138,7 @@  static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 	struct z3fold_header *zhdr = NULL;
 	struct page *page = NULL;
 	struct list_head *pos;
+	struct z3fold_buddy_slots slots;
 	unsigned long first_handle = 0, middle_handle = 0, last_handle = 0;
 
 	spin_lock(&pool->lock);
@@ -1150,16 +1157,22 @@  static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			/* this bit could have been set by free, in which case
 			 * we pass over to the next page in the pool.
 			 */
-			if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+			if (test_and_set_bit(PAGE_CLAIMED, &page->private)) {
+				page = NULL;
 				continue;
+			}
 
-			if (unlikely(PageIsolated(page)))
+			if (unlikely(PageIsolated(page))) {
+				clear_bit(PAGE_CLAIMED, &page->private);
+				page = NULL;
 				continue;
+			}
+			zhdr = page_address(page);
 			if (test_bit(PAGE_HEADLESS, &page->private))
 				break;
 
-			zhdr = page_address(page);
 			if (!z3fold_page_trylock(zhdr)) {
+				clear_bit(PAGE_CLAIMED, &page->private);
 				zhdr = NULL;
 				continue; /* can't evict at this point */
 			}
@@ -1177,26 +1190,30 @@  static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 
 		if (!test_bit(PAGE_HEADLESS, &page->private)) {
 			/*
-			 * We need encode the handles before unlocking, since
-			 * we can race with free that will set
-			 * (first|last)_chunks to 0
+			 * We need encode the handles before unlocking, and
+			 * use our local slots structure because z3fold_free
+			 * can zero out zhdr->slots and we can't do much
+			 * about that
 			 */
 			first_handle = 0;
 			last_handle = 0;
 			middle_handle = 0;
 			if (zhdr->first_chunks)
-				first_handle = encode_handle(zhdr, FIRST);
+				first_handle = __encode_handle(zhdr, &slots,
+								FIRST);
 			if (zhdr->middle_chunks)
-				middle_handle = encode_handle(zhdr, MIDDLE);
+				middle_handle = __encode_handle(zhdr, &slots,
+								MIDDLE);
 			if (zhdr->last_chunks)
-				last_handle = encode_handle(zhdr, LAST);
+				last_handle = __encode_handle(zhdr, &slots,
+								LAST);
 			/*
 			 * it's safe to unlock here because we hold a
 			 * reference to this page
 			 */
 			z3fold_page_unlock(zhdr);
 		} else {
-			first_handle = encode_handle(zhdr, HEADLESS);
+			first_handle = __encode_handle(zhdr, &slots, HEADLESS);
 			last_handle = middle_handle = 0;
 		}
 
@@ -1226,9 +1243,9 @@  static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			spin_lock(&pool->lock);
 			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
+			clear_bit(PAGE_CLAIMED, &page->private);
 		} else {
 			z3fold_page_lock(zhdr);
-			clear_bit(PAGE_CLAIMED, &page->private);
 			if (kref_put(&zhdr->refcount,
 					release_z3fold_page_locked)) {
 				atomic64_dec(&pool->pages_nr);
@@ -1243,6 +1260,7 @@  static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
 			z3fold_page_unlock(zhdr);
+			clear_bit(PAGE_CLAIMED, &page->private);
 		}
 
 		/* We started off locked to we need to lock the pool back */
@@ -1369,7 +1387,8 @@  static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 	VM_BUG_ON_PAGE(!PageMovable(page), page);
 	VM_BUG_ON_PAGE(PageIsolated(page), page);
 
-	if (test_bit(PAGE_HEADLESS, &page->private))
+	if (test_bit(PAGE_HEADLESS, &page->private) ||
+	    test_bit(PAGE_CLAIMED, &page->private))
 		return false;
 
 	zhdr = page_address(page);